© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14183
    Prev
    Next
    INDEX
    Explanations

    which events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unglaublich
    0.49
    laublich
    0.47
     jurusan
    0.46
     AREA
    0.45
     niemand
    0.44
    ל
    0.44
    ATTLE
    0.44
     kampus
    0.44
    ज्ञात
    0.43
     IUnary
    0.43
    POSITIVE LOGITS
     ръ
    0.46
    ሦ
    0.45
     ولكن
    0.44
    ματος
    0.44
     Instead
    0.44
     și
    0.43
     Elisa
    0.43
     δεί
    0.42
     للان
    0.42
     Rather
    0.41
    Activations Density 0.004%

    No Known Activations